Have you ever wondered what a Gyarados would look like as a fire type? Or grass type, or electric type?
For my last project at the Recurse Center, I trained CycleGAN, an image-to-image translation model, on images of Pokémon of different types.
The open-source implementation used to train and generate these images of Pokémon uses PyTorch and can be found on Github here. For this project, I trained the model to translate between sets of Pokémon images of different types, e.g. translating images of water types to fire types.
The original dataset of Pokémon images can be found here, containing Generations 1-7. The script I wrote to sort Pokémon images by their primary type can be found here, and the resulting sorted dataset of Pokémon images by primary type can be found on my Github here.
For each pair of images, on the left is the original image of the Pokemon, and on the right is the type-translated version. (Results are best viewed if you turn off f.lux, night shift, or any other display mode that changes the color of your screen.)